diff options
| author | Namhyung Kim <namhyung@kernel.org> | 2022-10-17 19:02:18 -0700 |
|---|---|---|
| committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2022-10-27 16:37:25 -0300 |
| commit | 050059e1b1affc080ede9fe691768e2383eb6367 (patch) | |
| tree | 0bf2b9c7fab722cbcb2756f0a39eba622a5c41c1 /tools/perf/util/stat.c | |
| parent | 049aba09e2156dd2ff1a61bf1b8738b0fc864c9d (diff) | |
| download | lwn-050059e1b1affc080ede9fe691768e2383eb6367.tar.gz lwn-050059e1b1affc080ede9fe691768e2383eb6367.zip | |
perf stat: Aggregate per-thread stats using evsel->stats->aggr
Per-thread aggregation doesn't use the CPU numbers but the logic should
be the same. Initialize cpu_aggr_map separately for AGGR_THREAD and use
thread map idx to aggregate counter values.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20221018020227.85905-12-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/stat.c')
| -rw-r--r-- | tools/perf/util/stat.c | 24 |
1 files changed, 22 insertions, 2 deletions
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index dc075d5a0f72..5b04c9d16156 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -422,6 +422,24 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel, evsel__compute_deltas(evsel, cpu_map_idx, thread, count); perf_counts_values__scale(count, config->scale, NULL); + if (config->aggr_mode == AGGR_THREAD) { + struct perf_counts_values *aggr_counts = &ps->aggr[thread].counts; + + /* + * Skip value 0 when enabling --per-thread globally, + * otherwise too many 0 output. + */ + if (count->val == 0 && config->system_wide) + return 0; + + ps->aggr[thread].nr++; + + aggr_counts->val += count->val; + aggr_counts->ena += count->ena; + aggr_counts->run += count->run; + goto update; + } + if (ps->aggr) { struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx); struct aggr_cpu_id aggr_id = config->aggr_get_id(config, cpu); @@ -436,8 +454,9 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel, ps_aggr->nr++; /* - * When any result is bad, make them all to give - * consistent output in interval mode. + * When any result is bad, make them all to give consistent output + * in interval mode. But per-task counters can have 0 enabled time + * when some tasks are idle. */ if (evsel__count_has_error(evsel, count, config) && !ps_aggr->failed) { ps_aggr->counts.val = 0; @@ -455,6 +474,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel, } } +update: switch (config->aggr_mode) { case AGGR_THREAD: case AGGR_CORE: |